publication

GitHub Copilot Automations adds outcome-feedback prompt self-improvement with human approval (28 Oct 2026)

GitHub released a Copilot Automations improvement on Oct28: automation outcomes (label reversals, accepted review comments, merged PRs) can feed another automation that proposes edits to original prompts, tools or triggers; a human must approve each proposed edit. This is a bounded, productized feedback loop, not recursive model-weight training or autonomous self-application, and no measured quality gain is published.

Original sources

Open artifact View JSON